GitHub
Connected
Repositories
Workflows
General Analysis raises $10MUnderstand your AI risk.
HIGHHIGHMEDIUMMEDIUMCRITICAL
End-to-end agent security.
Understand your AI risk.
Prevent incidents.
General Analysis helps security teams adversarially test, monitor, and protect AI agents and systems in production.
Discover
Map every AI asset across your stack.
Connect GitHub, your LLM providers, and your cloud runtime. We extract every model, vector store, MCP server, agent, and credential. Each is scanned for common vulnerabilities and scored by risk.
Data sources
GitHub
Connected
Repositories
Workflows
LLM Providers
Connected
System prompts
Tool schemas
OpenAIAnthropicGoogle
Cloud & Runtime
Connected
Cloud logs
Identity & access
awsgcpk8s
Ingesting & normalizing
Securely ingesting and normalizing telemetry from your tools.
Discovered surface
Analyze
Audit your stack against AI security best practices.
Unsafe model defaults, over-privileged agents, unverified MCPs, lethal-trifecta paths. Run compliance checks against NIST AI RMF, OWASP, and other standards, or against your own internal policies.
Scan in progress
$ ga scan --workspace prod-ai --scope all
[12s] discovering model endpoints
[19s] mapping MCP tools and permissions
[26s] checking runtime exposure
Coverage14%
Risks identified
normalized scan
Unsafe model from Hugging Face
mistralai/Mixtral-8x7B-Instruct-v0.1
Risky model detected: DeepSeek
deepseek-ai/deepseek-chat
Unofficial MCP server
mcp://community-weather-server
Over-permissive tool schema
filesystem.write + external_request
Lethal trifecta path detected
Prompt injection · Tool misuse · Data exfiltration
0 risks foundView all risks
Red-team
Run adversarial attacks against your agents.
Hundreds of simulations across prompt injection, tool misuse, sensitive retrieval, and multi-step exploit chains. Driven by post-trained attacker models that adapt to your defenses.
Attack simulation
$ ga redteam --target support-agent --scenario exfiltration
360 generated campaigns across models, MCPs, and runtime permissions
Attempts
42
Paths
7
Exploit path
confirmedPrompt injection
support ticket
Tool misuse
untrusted MCP
Data access
private KB
Exfil attempt
blocked egress
Injected policy override recovered from ticket body
Agent selected untrusted MCP server with network access
Sensitive retrieval attempted before outbound tool call
Remediate
Experiment until the configuration holds.
Combine guardrails, observability, system prompt hardening, identity management, and other controls. Re-run red-team experiments against each variant. Empirically drive attack success rate down.
Control experiment
$ ga remediate --apply-controls --validate-asr
replaying confirmed exploit chains against hardened configuration
Before replay
42%
After replay
0%
Applied controls
validatedCustom Guardrails Training
red-team examples
trained
System Prompt Hardening
constraints + refusals
hardened
Identity Management
least privilege
scoped
Observability
traces + alerts
active
Replay validation
Same exploit set
Before controls
42%
attacks succeeded
After controls
0%
replayed attacks held
Replayed confirmed exploit chains against the hardened configuration. Detailed outcomes are listed in Exploit checks.
Latest news and research
General Analysis raises $10M to build the security arsenal for the agentic era
Led by Altos Ventures, with 645 Ventures and Menlo Ventures participating, the round funds an empirical security platform pairing adversarial simulation with production defenses.
Guardrail Release
Open-source release of the GA Guard series, a family of safety classifiers that have been providing comprehensive protection for enterprise AI deployments for the past year.
Claude jailbroken to issue a $50,000 Stripe coupon
General AnalysisClaude Jailbroken to Mint Unlimited Stripe Coupons
We reveal a powerful metadata-spoofing attack that exploits Claude's iMessage integration to mint unlimited Stripe coupons or invoke any MCP tool with arbitrary parameters, without alerting the user.
Supabase MCP can leak your private SQL tables
General AnalysisSupabase MCP can leak your entire SQL database
Indirect prompt injection through support-ticket data lets an MCP-enabled assistant cross trust boundaries and query private tables with Supabase’s privileged service role.
The Redact & Recover jailbreak
General AnalysisExploiting Partial Compliance: The Redact-and-Recover Jailbreak
We present the Redact & Recover (RnR) Jailbreak, a novel attack that exploits partial compliance behaviors in frontier LLMs to bypass safety guardrails through a two-phase decomposition strategy.
